A python script to parse Facebook messenger data from your downloaded Facebook data and creates searchable html files of them

parse_facebook_archive.py

import os
import json
import re
import shutil
from pathlib import Path
from datetime import datetime
from argparse import ArgumentParser
from html import escape

MY_NAME = "YOUR NAME AS IT IS ON FB HERE"

MEDIA_TYPES = {
    "audio": [
        ".mp3",
        ".m4a",
        ".aac",
        ".wav",
        ".ogg",
        ".opus",
        ".flac",
        ".wma",
        ".aiff",
    ],
    "photos": [".jpg", ".jpeg", ".png", ".webp", ".heic", ".heif", ".tiff", ".bmp"],
    "gifs": [".gif"],
    "videos": [
        ".mp4",
        ".mov",
        ".mkv",
        ".avi",
        ".wmv",
        ".flv",
        ".webm",
        ".m4v",
        ".3gp",
        ".mpeg",
        ".mpg",
        ".rmvb",
        ".vob",
        ".ts",
    ],
    "files": [
        ".docx",
        ".pdf",
        ".txt",
        ".zip",
        ".pptx",
        ".xlsx",
        ".csv",
        ".rar",
        ".7z",
        ".tar",
        ".gz",
        ".bz2",
    ],
}


def readable_timestamp(ts_ms):
    return datetime.fromtimestamp(ts_ms / 1000).strftime("%m/%d/%Y %I:%M %p")


def linkify(text):
    def replacer(match):
        url = match.group(0)
        return f'<a href="{url}" target="_blank" rel="noopener noreferrer">{url}</a>'

    url_pattern = re.compile(r"(https?://[^\s]+)")
    return url_pattern.sub(replacer, text)


def parse_messages(json_files):
    all_messages = []
    participants = set()

    for file in sorted(json_files):
        try:
            with open(file, "r", encoding="utf-8") as f:
                data = json.load(f)
        except UnicodeDecodeError:
            with open(file, "r", encoding="utf-8", errors="replace") as f:
                data = json.load(f)

        participants.update(p.get("name") for p in data.get("participants", []))
        for msg in data.get("messages", []):
            if "content" in msg:
                all_messages.append(
                    {
                        "timestamp": msg["timestamp_ms"],
                        "sender": msg["sender_name"],
                        "content": linkify(escape(msg["content"], quote=False)),
                    }
                )

    all_messages.sort(key=lambda m: m["timestamp"])
    output_html = []
    for msg in all_messages:
        ts = readable_timestamp(msg["timestamp"])
        css_class = "from-me" if msg["sender"] == MY_NAME else "from-them"
        output_html.append(
            f"<p class='message {css_class}' data-sender='{msg['sender'].lower()}' data-content='{msg['content'].lower()}'><strong>[{ts}]</strong> <span class='sender'>{escape(msg['sender'])}</span>: <span class='content'>{msg['content']}</span></p>"
        )
    return "\n".join(output_html), participants


def generate_media_previews(folder, rel_url):
    if not folder.exists():
        return ""
    previews = ""
    for file in sorted(folder.iterdir()):
        ext = file.suffix.lower()
        url = f"{rel_url}/{file.name}"
        if ext in MEDIA_TYPES["photos"] + MEDIA_TYPES["gifs"]:
            previews += (
                f"<div class='media-box'><img src='{url}' class='img-fluid'></div>"
            )
        elif ext in MEDIA_TYPES["videos"]:
            previews += f"<div class='media-box'><video controls width='100%'><source src='{url}' type='video/mp4'></video></div>"
        elif ext in MEDIA_TYPES["audio"]:
            previews += f"<div class='media-box'><audio controls><source src='{url}'></audio></div>"
    return previews


def generate_media_table(folder, rel_url):
    if not folder.exists():
        return ""
    rows = ""
    for file in sorted(folder.iterdir()):
        if file.is_file():
            ext = file.suffix.replace(".", "").upper()
            rows += f"<tr><td>{escape(file.name)}</td><td>{ext}</td><td><a href='{rel_url}/{file.name}' target='_blank'>View</a></td></tr>"
    if rows:
        return f"<h3>{folder.name.title()} Files</h3><table class='table table-sm table-dark table-striped'><thead><tr><th>Filename</th><th>Type</th><th>View/Download</th></tr></thead><tbody>{rows}</tbody></table>"
    return ""


def copy_media_dirs(convo_dir, output_convo_dir):
    for media_folder in MEDIA_TYPES:
        src = convo_dir / media_folder
        dst = output_convo_dir / media_folder
        if src.exists() and src.is_dir():
            shutil.copytree(src, dst, dirs_exist_ok=True)


def generate_html_page(
    title, messages_html, media_tables, media_previews, participants
):
    participants_html = (
        "<p id='participants' ><strong>Participants:</strong> "
        + ", ".join(escape(p) for p in sorted(participants))
        + "</p>"
        if participants
        else ""
    )
    return f"""
    <!DOCTYPE html>
    <html lang='en'>
<head>
<meta charset='UTF-8'>
<title>{escape(title)}</title>
<link href='https://cdn.jsdelivr.net/npm/bootstrap@latest/dist/css/bootstrap.min.css' rel='stylesheet'>
<link href='https://cdn.jsdelivr.net/npm/@fortawesome/fontawesome-free@latest/css/all.min.css' rel='stylesheet'>
<link href='https://cdn.jsdelivr.net/npm/sweetalert2@latest/dist/sweetalert2.min.css' rel='stylesheet'>
<link href='https://cdn.jsdelivr.net/npm/tippy.js@latest/dist/tippy.css' rel='stylesheet'>
<link href='assets/css/all.css' rel='stylesheet'>
<style>
    body {{ background: #222222; color: #F5F5F5; font-family: monospace; padding: 20px; }}
    .media-box {{ margin: 10px 0; }}
    .chat-log p {{ margin-bottom: 5px; }}
    #search {{ width: 100%; margin-bottom: 20px; padding: 10px; border-radius: 5px; border: none; }}
    .from-me {{ color: #0fd5db; }}
    .from-them {{ color: #9bff7d; }}
    .p {{ margin-top: 5px; margin-bottom: 5px; }}
    #participants {{ font-size="32" text-align: "center"; margin-bottom: 20px; }}
</style>
</head>
<body>
<h1 class='text-warning text-center'>
    {escape(title)}
</h1>
{participants_html}
<input id='search' type='text' placeholder='Search by sender or message...' />
<div class='chat-log'>
    {messages_html}
</div>
<hr/>
{media_previews}
{media_tables}
<script>
document.getElementById('search').addEventListener('input', function(e) {{
  const value = e.target.value.toLowerCase();
  document.querySelectorAll('.message').forEach(msg => {{
    const sender = msg.dataset.sender || '';
    const content = msg.dataset.content || '';
    msg.style.display = (sender.includes(value) || content.includes(value)) ? 'block' : 'none';
  }});
}});
</script>
<script src='https://cdn.jsdelivr.net/npm/bootstrap@latest/dist/js/bootstrap.bundle.min.js'></script>
<script src='https://cdn.jsdelivr.net/npm/sweetalert2@latest/dist/sweetalert2.all.min.js'></script>
<script src='https://cdn.jsdelivr.net/npm/tippy.js@latest/dist/tippy-bundle.umd.min.js'></script>
<script src='https://cdn.jsdelivr.net/npm/clipboard@latest/dist/clipboard.min.js'></script>
<script src='https://cdn.jsdelivr.net/npm/clipboard-polyfill@latest/dist/clipboard-polyfill.min.js'></script>
<script src='assets/js/all.js'></script>
</body>
</html>
"""


def build_convo_html(convo_dir, output_dir, rel_output_path):
    json_files = list(convo_dir.glob("*.json"))
    if not json_files:
        return None
    messages_html, participants = parse_messages(json_files)
    media_html = ""
    tables_html = ""
    for folder_name in MEDIA_TYPES:
        media_path = convo_dir / folder_name
        rel_url = f"./{folder_name}" if media_path.exists() else ""
        media_html += generate_media_previews(media_path, rel_url)
        tables_html += generate_media_table(media_path, rel_url)

    output_path = output_dir / rel_output_path / "index.html"
    output_path.parent.mkdir(parents=True, exist_ok=True)
    copy_media_dirs(convo_dir, output_path.parent)

    try:
        with open(json_files[0], "r", encoding="utf-8") as f:
            title = json.load(f).get("title", convo_dir.name)
    except:
        title = convo_dir.name

    with open(output_path, "w", encoding="utf-8") as f:
        f.write(
            generate_html_page(
                title, messages_html, tables_html, media_html, participants
            )
        )

    return str(rel_output_path).replace("\\", "/")


def build_index(all_convos, output_dir):
    sections = ""
    for section, convos in all_convos.items():
        links = "\n".join(
            [
                f"<li class='list-group-item bg-dark'><a class='text-warning' href='{c}/index.html'>{c}</a></li>"
                for c in sorted(convos)
            ]
        )
        sections += f"<h2 class='text-warning'>{section.title()}</h2><ul class='list-group mb-4'>{links}</ul>"

    html = f"""<!DOCTYPE html>
    <html lang='en'>
    <head>
        <meta charset='UTF-8'>
        <title>Messenger Archive</title>
        <link href='https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css' rel='stylesheet'>
    </head>
    <body class='bg-dark text-light'>
    <div class='container mt-5'>
        <h1 class='text-warning text-center mb-5'>
            Facebook Messenger Archive
        </h1>
        {sections}
    </div>
    </body>
    </html>"""
    with open(output_dir / "index.html", "w", encoding="utf-8") as f:
        f.write(html)


def process_all(root_input, output_root):
    categories = [
        "inbox",
        "archived_threads",
        "e2ee_cutover",
        "stickers_used",
        "support_files",
    ]
    all_convos = {}

    for category in categories:
        input_path = Path(root_input) / category
        if not input_path.exists():
            continue
        for convo_dir in input_path.iterdir():
            if convo_dir.is_dir():
                rel_path = Path(category) / convo_dir.name
                result = build_convo_html(convo_dir, output_root, rel_path)
                if result:
                    all_convos.setdefault(category, []).append(result)

    build_index(all_convos, output_root)


if __name__ == "__main__":
    parser = ArgumentParser(
        description="Parse Facebook Messenger export into HTML archive."
    )
    parser.add_argument(
        "messages_folder",
        help="Path to 'messages' folder (contains inbox/, archived_threads/, e2ee_cutover/)",
    )
    parser.add_argument("--output", help="Output folder", default="output_html")
    args = parser.parse_args()

    process_all(args.messages_folder, Path(args.output).resolve())

Get your Facebook data from Facebook. Once you have it, unzip it to wherever and put this script inside the root folder of wherever you unzipped the data. By default, this script parses data in facebook_data\your_facebook_activity\messages